Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.3985. Min Act: -0.1700
Data Index: 6948297 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.3720. Min Act: -0.1700
Data Index: 1992756 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.3456. Min Act: -0.1680
Data Index: 1918063 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.3015. Min Act: -0.1700
Data Index: 8207042 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2927. Min Act: -0.1411
Data Index: 5465278 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2927. Min Act: -0.1700
Data Index: 6983795 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2927. Min Act: -0.1700
Data Index: 4730717 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2838. Min Act: -0.1700
Data Index: 7262948 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2838. Min Act: -0.1700
Data Index: 1548961 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2838. Min Act: -0.1693
Data Index: 1703831 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2750. Min Act: -0.1700
Data Index: 2679515 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2750. Min Act: -0.1700
Data Index: 2937517 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2838. Min Act: -0.1700
Data Index: 5771700 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2662. Min Act: -0.1693
Data Index: 3998760 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2662. Min Act: -0.1699
Data Index: 8123629 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2574. Min Act: -0.1700
Data Index: 3461955 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2574. Min Act: -0.1699
Data Index: 1745924 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2662. Min Act: -0.1700
Data Index: 6822799 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2574. Min Act: -0.1700
Data Index: 2921923 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3985. Min Range: -1.3985
Max Act: 1.2486. Min Act: -0.1700
Data Index: 2527277 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19